club-3090
Hacker ApprovedInference setup guide in AI tools
People recommend it for verified configs and writeups for running local Qwen and Gemma models on one or two GPUs, with documented context window tradeoffs.
People recommend it for verified configs and writeups for running local Qwen and Gemma models on one or two GPUs, with documented context window tradeoffs.
12 people gave an opinion
- recommend it
- 11
- criticize it
- 1
- approval share
- 92%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 11 people recommend itNeeds 10 or more, met.
- 11 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Verified setups for Qwen and Gemma
“Qwen3.6 27b has been rock solid using club 3090's single card setup for agentic use”
Comment from 16 Jun 2026 in “Running local models is good now” “I'd jump right into verified set-ups and writeups, like this one”
Comment from 18 Jun 2026 in “Local Qwen isn't a worse Opus, it's a different tool” “optimized configs for Qwen and Gema models”
Comment from 29 Jun 2026 in “Qwen 3.6 27B is the sweet spot for local development” Simplifies installing local LLMs on GPUs
“I've heard that club 3090 makes that relatively straightforward”
Comment from 2 Jul 2026 in “Kimi K2.7 Code is generally available in GitHub Copilot” “Club 3090 will make installing llm easier, for 1 or more cards.”
Comment from 18 Jul 2026 in “GTX 1080s: Testing a Legend” Documents context window tradeoffs
“fast inference at the cost of a reduced 102k context window”
Comment from 3 Jul 2026 in “Jamesob's guide to running SOTA LLMs locally” “Full 262k context, usable in oh-my-pi.”
Comment from 8 May 2026 in “ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math” Referenced for alternative setups
“I need to try out some of the other set ups mentioned in this repo for increased TPS.”
Comment from 30 Apr 2026 in “Granite 4.1: IBM's 8B Model Matching 32B MoE” “using the config from https://github.com/noonghunna/club-3090”
Comment from 14 Aug 2026 in “Qwen3.8-27B”
What people said
12 of the 14 comments that mention it, newest first. Each links to the original comment.
“For our mere mortals that were kids not long ago”
“I've looked at the club-3090 repo, but haven't found anything meaningful”
“using the config from https://github.com/noonghunna/club-3090”
“Club 3090 will make installing llm easier, for 1 or more cards.”
“fast inference at the cost of a reduced 102k context window”
“I've heard that club 3090 makes that relatively straightforward”
“optimized configs for Qwen and Gema models”
“This is a good place to start reading about dual gpus.”
“I'd jump right into verified set-ups and writeups, like this one”
“Qwen3.6 27b has been rock solid using club 3090's single card setup for agentic use”
“Full 262k context, usable in oh-my-pi.”
“I need to try out some of the other set ups mentioned in this repo for increased TPS.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.